Training in progress, step 24500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a5bf7d80afb43e227b324a1b6cda7e106c37feb23b0824b268c18e7b3a3d1a
+oid sha256:3030d4ce44a28d2687854bece3d36dd11a2483143dc2362c64bdaf84a148a35c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd314d98a4869313e973a437be445c914aa71bb8b03a7af5f6f9a32ad34d63bf
+oid sha256:8336f578c2856a2611344b57de4fde614962159ed2c75eff7de5a881717f1aa8
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727aa5fd6a222ba79327243b6bf0f36bc88c1b723f0949eac077fe52d4306974
+oid sha256:b7a44025f64c6f7ad3ba883de4c1f4995d535cdd50931b810e0a7d00e22e5cdc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:751ad724592c1d67b441302a9338d9d899df51042c6edaf69d5d08369bc3c9df
+oid sha256:6d9ad9a351ae61b83248fa17cb95ac2021f5fe42e6699ef47e0f8bde893c34bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6,
+  "epoch": 1.6333333333333333,
   "eval_steps": 500,
-  "global_step": 24000,
+  "global_step": 24500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1695,6 +1695,41 @@
       "learning_rate": 9.33688888888889e-06,
       "loss": 0.0581,
       "step": 24000
+    },
+    {
+      "epoch": 1.6066666666666667,
+      "grad_norm": 0.19345501065254211,
+      "learning_rate": 9.292444444444445e-06,
+      "loss": 0.0587,
+      "step": 24100
+    },
+    {
+      "epoch": 1.6133333333333333,
+      "grad_norm": 0.11753817647695541,
+      "learning_rate": 9.248e-06,
+      "loss": 0.0553,
+      "step": 24200
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.3054827153682709,
+      "learning_rate": 9.203555555555557e-06,
+      "loss": 0.0552,
+      "step": 24300
+    },
+    {
+      "epoch": 1.6266666666666667,
+      "grad_norm": 0.2914266884326935,
+      "learning_rate": 9.159111111111112e-06,
+      "loss": 0.0534,
+      "step": 24400
+    },
+    {
+      "epoch": 1.6333333333333333,
+      "grad_norm": 0.21610131859779358,
+      "learning_rate": 9.114666666666668e-06,
+      "loss": 0.0613,
+      "step": 24500
     }
   ],
   "logging_steps": 100,
@@ -1714,7 +1749,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.845995749376e+16,
+  "total_flos": 5.967787327488e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null